摘要
量子遗传算法的早熟问题影响算法的求解性能,为提高算法能力,提出基于混合蛙跳的量子遗传算法。算法引入混合蛙跳和模拟退火准则,采用量子变异策略;利用组内寻优和整体寻优,减少算法整体迭代次数。将改进后的量子遗传算法应用于函数优化方面,用测试函数的寻优来评价算法性能,实验结果表明,该算法有效提高了算法性能,能求解出符合要求的全局最优值,改善了早熟收敛的问题。
The problem of premature convergence of quantum genetic algorithm affects the solving performance of algorithm, to improve the algorithm's ability, the quantum genetic algorithm based on the shuffled frog leaping was proposed. The shuffled frog leaping algorithm and simulated annealing were introduced, while the quantum mutation strategy was used. The group opti- mization and the global optimization were used to reduce the overall number of iterative algorithms. The improved quantum genetic algorithm was applied to the functions optimization, test functions were used to evaluate the optimization algorithm's performance. The experimental results show that, the proposed algorithm improves the performance of the algorithm, and it can meet the requirements on solving the global optimum value and improve the premature convergence problem.
出处
《计算机工程与设计》
CSCD
北大核心
2014年第11期3991-3996,共6页
Computer Engineering and Design
基金
国家自然科学基金项目(61173056)
关键词
量子遗传
分组寻优
模拟退火
自适应
函数优化
quantum genetic
grouping optimization
simulated annealing
adaptive
function optimization